WRMR and multigroup models PreviousNext
Mplus Discussion > Structural Equation Modeling >
 Anonymous posted on Friday, January 04, 2013 - 8:43 am
I am looking for some (relatively recent) guidelines/literature on the use of the WRMR as part of the process for assessing model fit in multigroup models. I note that values of <1 are often regarded as indicative of satisfactory fit, however in one of your handouts regarding CFA testing there is a comment that the WRMR is not good with multigroup models. Hence I am looking for clarification on the matter. Thank you
 Linda K. Muthen posted on Friday, January 04, 2013 - 9:50 am
I would not use WRMR. It is an experimental fit statistic that has not been well studied. As you mention, we have found it does not work well in a multiple group setting.
 Anonymous posted on Saturday, January 05, 2013 - 10:34 am
Thank you. Do you know of any references I can cite regarding use of WRMR in multiple group settings?
 Bengt O. Muthen posted on Saturday, January 05, 2013 - 4:18 pm
I don't think Yu's dissertation covered that and I don't recall seeing it discussed.
Back to top
Add Your Message Here
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Options: Enable HTML code in message
Automatically activate URLs in message